AVOA: Energy and Resource Aware Scheduling Through Cloud Environment
Prashanthi Aindala, Kaushik Shivakumar, Paladugula Haripriya, Ramagowni Sivakumar, Rakesh Kumar Donthi, Santhosh Kumar Medishetti
Abstract
Effective scheduling of tasks in cloud computing is important in terms of maximizing resource usage, minimizing execution time, and lowering energy usage. This paper introduces a new scheduling method based on the African Vultures Optimization Algorithm (AVOA), which is motivated by the cooperative hunting behavior of vultures in Africa. AVOA efficiently explores and exploits the search space ensuring optimal task allocation to available Virtual Machines (VMs) while addressing challenges such as high makespan, energy inefficiency, and load imbalance. The proposed AVOA-based scheduling strategy dynamically adapts to varying workloads, prioritizing tasks based on computational requirements and resource availability. By integrating adaptive learning and competition-based selection, AVOA enhances convergence speed and solution quality. Simulation results demonstrate that AVOA outperforms traditional metaheuristic algorithms, achieving a 19.8% reduction in makespan, a 17.3% decrease in energy consumption, and a 22.1% improvement in resource utilization. Furthermore, AVOA’s robustness in handling large-scale cloud environments ensures improved Quality of Service (QoS), supporting diverse applications in real-time and data-intensive computing. The findings highlight the algorithm’s potential to enhance cloud performance, making it a promising solution for energy-efficient and cost-effective task scheduling. Future work will explore hybrid models integrating AVOA with deep learning techniques for further optimization.